{"ID":2893112,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13934","arxiv_id":"2507.13934","title":"DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization","abstract":"Unsupervised disentanglement of static appearance and dynamic motion in video remains a fundamental challenge, often hindered by information leakage and blurry reconstructions in existing VAE- and GAN-based approaches. We introduce DiViD, the first end-to-end video diffusion framework for explicit static-dynamic factorization. DiViD's sequence encoder extracts a global static token from the first frame and per-frame dynamic tokens, explicitly removing static content from the motion code. Its conditional DDPM decoder incorporates three key inductive biases: a shared-noise schedule for temporal consistency, a time-varying KL-based bottleneck that tightens at early timesteps (compressing static information) and relaxes later (enriching dynamics), and cross-attention that routes the global static token to all frames while keeping dynamic tokens frame-specific. An orthogonality regularizer further prevents residual static-dynamic leakage. We evaluate DiViD on real-world benchmarks using swap-based accuracy and cross-leakage metrics. DiViD outperforms state-of-the-art sequential disentanglement methods: it achieves the highest swap-based joint accuracy, preserves static fidelity while improving dynamic transfer, and reduces average cross-leakage.","short_abstract":"Unsupervised disentanglement of static appearance and dynamic motion in video remains a fundamental challenge, often hindered by information leakage and blurry reconstructions in existing VAE- and GAN-based approaches. We introduce DiViD, the first end-to-end video diffusion framework for explicit static-dynamic factor...","url_abs":"https://arxiv.org/abs/2507.13934","url_pdf":"https://arxiv.org/pdf/2507.13934v2","authors":"[\"Marzieh Gheisari\",\"Auguste Genovesio\"]","published":"2025-07-18T14:09:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Generative Adversarial Network\",\"Variational Autoencoder\"]","has_code":false}